Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness

TL;DR

This paper introduces a probabilistic topometric localization system that effectively handles appearance changes and route deviations by integrating full odometry and an off-map state, improving localization accuracy.

Contribution

The novel system incorporates full 3-DOF odometry into the motion model and adds an off-map state to handle route deviations, advancing probabilistic localization methods.

Findings

Significant performance improvements over existing systems.

Effective localization despite appearance changes and route deviations.

Validated on Oxford RobotCar dataset for loop closure and global localization.

Abstract

Probabilistic state-estimation approaches offer a principled foundation for designing localization systems, because they naturally integrate sequences of imperfect motion and exteroceptive sensor data. Recently, probabilistic localization systems utilizing appearance-invariant visual place recognition (VPR) methods as the primary exteroceptive sensor have demonstrated state-of-the-art performance in the presence of substantial appearance change. However, existing systems 1) do not fully utilize odometry data within the motion models, and 2) are unable to handle route deviations, due to the assumption that query traverses exactly repeat the mapping traverse. To address these shortcomings, we present a new probabilistic topometric localization system which incorporates full 3-dof odometry into the motion model and furthermore, adds an "off-map" state within the state-estimation framework, allowing query traverses which feature significant route detours from the reference map to be successfully localized. We perform extensive evaluation on multiple query traverses from the Oxford RobotCar dataset exhibiting both significant appearance change and deviations from routes previously traversed. In particular, we evaluate performance on two practically relevant localization tasks: loop closure detection and global localization. Our approach achieves major performance improvements over both existing and improved state-of-the-art systems.